An empirical analysis of binary transformation strategies and base algorithms for multi-label learning

Autor(es)

Rivolli, Adriano ^[1] ; Read, Jesse ^[2] ; Soares, Carlos ^{[3, 4]} ; Pfahringer, Bernhard ^[5] ; de Carvalho, Andre C. P. L. F. ^{[6, 7]}

Afiliação do(s) autor(es)

^[1] Technol Univ Parana, Dept Comp Sci, Cornelio Procopio, Parana - Brazil

^[2] Ecole Polytech, Lab Informat LIX, Palaiseau - France

^[3] Univ Porto, Fraunhofer AICOS, Porto - Portugal

^[4] Univ Porto, LIAAD INESC TEC, Porto - Portugal

^[5] Univ Waikato, Hamilton - New Zealand

^[6] Univ Sao Paulo, Inst Math & Comp Sci, Sao Carlos, SP - Brazil

^[7] Univ Sao Paulo, Inst Math & Comp Sci, Sao Carlos, SP, Brazil.Rivolli, Adriano, Technol Univ Parana, Dept Comp Sci, Cornelio Procopio, Parana - Brazil

• Tipo de documento: Artigo Científico
• Fonte: MACHINE LEARNING; v. 109, n. 8 JUN 2020.
• Citações Web of Science: 0

Resumo

Investigating strategies that are able to efficiently deal with multi-label classification tasks is a current research topic in machine learning. Many methods have been proposed, making the selection of the most suitable strategy a challenging issue. From this premise, this paper presents an extensive empirical analysis of the binary transformation strategies and base algorithms for multi-label learning. This subset of strategies uses the one-versus-all approach to transform the original data, generating one binary data set per label, upon which any binary base algorithm can be applied. Considering that the influence of the base algorithm on the predictive performance obtained by the strategies has not been considered in depth by many empirical studies, we investigated the influence of distinct base algorithms on the performance of several strategies. Thus, this study covers a family of multi-label strategies using a diversified range of base algorithms, exploring their relationship over different perspectives. This finding has significant implications concerning the methodology of evaluation adopted in multi-label experiments containing binary transformation strategies, given that multiple base algorithms should be considered. Despite these improvements in strategy and base algorithms, for many data sets, a large number of labels, mainly those less frequent, were either never predicted, or always misclassified. We conclude the experimental analysis by recommending strategies and base algorithms in accordance with different performance criteria. (AU)

• Processo FAPESP: 16/18615-0 - Aprendizado de máquina avançado
• Beneficiário: André Carlos Ponce de Leon Ferreira de Carvalho
• Modalidade de apoio: Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE
• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 12/22608-8 - Uso de medidas de complexidade de dados no suporte ao aprendizado de máquina supervisionado
• Beneficiário: Ana Carolina Lorena
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores